And communications the republic of uzbekistan tashkent university of information technologies

Thermal cameras 
A different form of taking input data for face recognition is by using thermal 
cameras, by this procedure the cameras will only detect the shape of the head and it 
will ignore the subject accessories such as glasses, hats, or make up. A problem 
with using thermal pictures for face recognition is that the databases for face 
recognition is limited. Diego Socolinsky, and Andrea Slinger (2004) research the 
use of thermal face recognition in real life, and operation sceneries, and at the same 
time build a new database of thermal facial images. The research uses low-
sensitive, low-resolution Ferro-electric electrics sensors that are capable of acquire 
long wave thermal infrared (LWIR). The results show that a fusion of LWIR and 
regular visual cameras has the greater results in outdoor probes. Indoor results 
show that visual has a 97.05% accuracy, while LWIR has 93.93%, and the Fusion 
has 98.40%, however on the outdoor proves visual has 67.06%, LWIR 83.03%, 
and fusion has 89.02%. The study used 240 subjects over the period of 10 weeks to 
create the new database. The data was collected on sunny, rainy, and cloudy days. 
Notable users and deployments 

---

The Australian and New Zealand Customs Services have an automated 
border processing system called Smart Gate that uses facial recognition. The 
system compares the face of the individual with the image in the e-
passport microchip to verify that the holder of the passport is the rightful owner. 
Law enforcement agencies in the United States, including the Los Angeles County 
Sheriff, use arrest mug shot databases in their forensic investigative work. As of 
2013, there is no unified nationwide database of face pictures mapping to names, 
but there are some efforts to create one. 
U.S. Department of State operates one of the largest face recognition 
systems in the world with over 75 million photographs that is actively used 
for visa processing. The FBI has also instituted its Next Generation Identification 
program to include facial recognition, as well as more traditional biometrics like 
fingerprints and iris scans, which can pull from both criminal and civil databases. 
The Tucuman International Airport in Panama operates an airport-wide 
surveillance system using hundreds of live facial recognition cameras to identify 
wanted individuals passing through the airport. 
Additional uses 
In addition to being used for security systems, authorities have found a 
number of other applications for facial recognition systems. While earlier post-
9/11 deployments were well publicized trials, more recent deployments are rarely 
written about due to their covert nature. 
At Super Bowl XXXV in January 2001, police in Tampa Bay, Florida used 
Visage facial recognition software to search for potential criminals and terrorists in 
attendance at the event. 19 people with minor criminal records were potentially 
identified. 
In the 2000 presidential election, the Mexican government employed facial 
recognition software to prevent voter fraud. Some individuals had been registering 
to vote under several different names, in an attempt to place multiple votes. By 
comparing new facial images to those already in the voter database, authorities 

---

were able to reduce duplicate registrations. Similar technologies are being used in 
the United States to prevent people from obtaining fake identification cards and 
driver’s licenses[11]. 
There are also a number of potential uses for facial recognition that are 
currently being developed. For example, the technology could be used as a security 
measure at ATMs. Instead of using a bank card or personal identification number, 
the ATM would capture an image of the customer's face, and compare it to the 
account holder's photo in the bank database to confirm the customer's identity. 
Facial recognition systems are used to unlock software on mobile devices. 
An independently developed Android Marketplace app called Vision App lock 
makes use of the phone's built-in camera to take a picture of the user. Facial 
recognition is used to ensure only this person can use certain apps which they 
choose to secure. Face detection and facial recognition are integrated into 
the iPhoto application for Macintosh, to help users organize and caption their 
collections. 
Also, in addition to biometric usages, modern digital cameras often 
incorporate a facial detection system that allows the camera to focus and measure 
exposure on the face of the subject, thus guaranteeing a focused portrait of the 
person being photographed. Some cameras, in addition, incorporate a smile shutter, 
or automatically take a second picture if someone blinks during exposure. 
Because of certain limitations of fingerprint recognition systems, facial recognition 
systems are used as an alternative way to confirm employee attendance at work for 
the claimed hours. Another use could be a portable device to assist people with 
prosopagnosia in recognizing their acquaintances.